Hugging Face's logo

yahyaabd
/
allstats-search-distiluse-v1

Sentence Similarity
sentence-transformers
Safetensors
Indonesian
distilbert
feature-extraction
Generated from Trainer
dataset_size:42138
loss:CosineSimilarityLoss
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
yahyaabd commited on
Commit
7f408af
·
verified ·
1 Parent(s): ed1f3a0

Add new SentenceTransformer model

Browse files
Files changed (13) hide show
  1. 1_Pooling/config.json +10 -0
  2. 2_Dense/config.json +1 -0
  3. 2_Dense/model.safetensors +3 -0
  4. README.md +559 -0
  5. config.json +26 -0
  6. config_sentence_transformers.json +10 -0
  7. model.safetensors +3 -0
  8. modules.json +20 -0
  9. sentence_bert_config.json +4 -0
  10. special_tokens_map.json +37 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +67 -0
  13. vocab.txt +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
2_Dense/config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"in_features": 768, "out_features": 512, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}
2_Dense/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93676f083ca6a157e750f80889c75bbdce6cc5837d497f2ca074261706fc0da0
3
+ size 1575072
README.md ADDED
@@ -0,0 +1,559 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - id
4
+ tags:
5
+ - sentence-transformers
6
+ - sentence-similarity
7
+ - feature-extraction
8
+ - generated_from_trainer
9
+ - dataset_size:42138
10
+ - loss:CosineSimilarityLoss
11
+ base_model: sentence-transformers/distiluse-base-multilingual-cased-v2
12
+ widget:
13
+ - source_sentence: Informasi importir Indonesia 2014 (Jilid Kedua)
14
+ sentences:
15
+ - Indikator Konstruksi Triwulan IV-2011
16
+ - Benchmark Indeks Konstruksi (2010=100), 1990-2013
17
+ - Statistik Upah Q-2 2002-Q-2 2004
18
+ - source_sentence: Direktori Perusahaan Penggiling Padi Aceh 2012
19
+ sentences:
20
+ - Direktori Perusahaan Industri Penggilingan Padi Tahun 2012 Provinsi Aceh
21
+ - Buletin Statistik Perdagangan Luar Negeri Ekspor Menurut Kelompok Komoditi dan
22
+ Negara, Agustus 2024
23
+ - Statistik Harga Produsen Pertanian Subsektor Tanaman Pangan, Hortikultura, dan
24
+ Tanaman Perkebunan Rakyat 2022
25
+ - source_sentence: Neraca pemerintahan pusat triwulanan 2015-2021:2
26
+ sentences:
27
+ - Tinjauan Regional Berdasarkan PDRB Kabupaten/Kota 2017- 2021, Buku 1 Pulau Sumatera
28
+ - Statistik Tebu Indonesia 2020
29
+ - Indikator Pasar Tenaga Kerja Indonesia Agustus 2011
30
+ - source_sentence: Data pembangunan kuartal kedua 2014
31
+ sentences:
32
+ - Katalog Publikasi BPS 2018
33
+ - Indikator Konstruksi Triwulan II-2014
34
+ - Produk Domestik Regional Bruto Provinsi-provinsi di Indonesia Menurut Penggunaan
35
+ 2004-2008
36
+ - source_sentence: Laporan keuangan pemerintah provinsi periode 2003-2006
37
+ sentences:
38
+ - Statistik Perdagangan Luar Negeri Indonesia Ekspor Menurut Kode ISIC 2013-2014
39
+ - Statistik Keuangan Provinsi 2003-2006
40
+ - Statistik Industri Manufaktur Indonesia 2013
41
+ datasets:
42
+ - yahyaabd/bps-publication-title-pairs
43
+ pipeline_tag: sentence-similarity
44
+ library_name: sentence-transformers
45
+ metrics:
46
+ - pearson_cosine
47
+ - spearman_cosine
48
+ model-index:
49
+ - name: SentenceTransformer based on sentence-transformers/distiluse-base-multilingual-cased-v2
50
+ results:
51
+ - task:
52
+ type: semantic-similarity
53
+ name: Semantic Similarity
54
+ dataset:
55
+ name: allstat semantic dev
56
+ type: allstat-semantic-dev
57
+ metrics:
58
+ - type: pearson_cosine
59
+ value: 0.9659430111615187
60
+ name: Pearson Cosine
61
+ - type: spearman_cosine
62
+ value: 0.8744991009318857
63
+ name: Spearman Cosine
64
+ - task:
65
+ type: semantic-similarity
66
+ name: Semantic Similarity
67
+ dataset:
68
+ name: allstat semantic test
69
+ type: allstat-semantic-test
70
+ metrics:
71
+ - type: pearson_cosine
72
+ value: 0.9645449367522956
73
+ name: Pearson Cosine
74
+ - type: spearman_cosine
75
+ value: 0.8645918683015844
76
+ name: Spearman Cosine
77
+ ---
78
+
79
+ # SentenceTransformer based on sentence-transformers/distiluse-base-multilingual-cased-v2
80
+
81
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/distiluse-base-multilingual-cased-v2](https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2) on the [bps-publication-title-pairs](https://huggingface.co/datasets/yahyaabd/bps-publication-title-pairs) dataset. It maps sentences & paragraphs to a 512-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
82
+
83
+ ## Model Details
84
+
85
+ ### Model Description
86
+ - **Model Type:** Sentence Transformer
87
+ - **Base model:** [sentence-transformers/distiluse-base-multilingual-cased-v2](https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2) <!-- at revision dad0fa1ee4fa6e982d3adbce87c73c02e6aee838 -->
88
+ - **Maximum Sequence Length:** 128 tokens
89
+ - **Output Dimensionality:** 512 dimensions
90
+ - **Similarity Function:** Cosine Similarity
91
+ - **Training Dataset:**
92
+ - [bps-publication-title-pairs](https://huggingface.co/datasets/yahyaabd/bps-publication-title-pairs)
93
+ - **Language:** id
94
+ <!-- - **License:** Unknown -->
95
+
96
+ ### Model Sources
97
+
98
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
99
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
100
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
101
+
102
+ ### Full Model Architecture
103
+
104
+ ```
105
+ SentenceTransformer(
106
+ (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel
107
+ (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
108
+ (2): Dense({'in_features': 768, 'out_features': 512, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
109
+ )
110
+ ```
111
+
112
+ ## Usage
113
+
114
+ ### Direct Usage (Sentence Transformers)
115
+
116
+ First install the Sentence Transformers library:
117
+
118
+ ```bash
119
+ pip install -U sentence-transformers
120
+ ```
121
+
122
+ Then you can load this model and run inference.
123
+ ```python
124
+ from sentence_transformers import SentenceTransformer
125
+
126
+ # Download from the 🤗 Hub
127
+ model = SentenceTransformer("yahyaabd/f-sts")
128
+ # Run inference
129
+ sentences = [
130
+ 'Laporan keuangan pemerintah provinsi periode 2003-2006',
131
+ 'Statistik Keuangan Provinsi 2003-2006',
132
+ 'Statistik Perdagangan Luar Negeri Indonesia Ekspor Menurut Kode ISIC 2013-2014',
133
+ ]
134
+ embeddings = model.encode(sentences)
135
+ print(embeddings.shape)
136
+ # [3, 512]
137
+
138
+ # Get the similarity scores for the embeddings
139
+ similarities = model.similarity(embeddings, embeddings)
140
+ print(similarities.shape)
141
+ # [3, 3]
142
+ ```
143
+
144
+ <!--
145
+ ### Direct Usage (Transformers)
146
+
147
+ <details><summary>Click to see the direct usage in Transformers</summary>
148
+
149
+ </details>
150
+ -->
151
+
152
+ <!--
153
+ ### Downstream Usage (Sentence Transformers)
154
+
155
+ You can finetune this model on your own dataset.
156
+
157
+ <details><summary>Click to expand</summary>
158
+
159
+ </details>
160
+ -->
161
+
162
+ <!--
163
+ ### Out-of-Scope Use
164
+
165
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
166
+ -->
167
+
168
+ ## Evaluation
169
+
170
+ ### Metrics
171
+
172
+ #### Semantic Similarity
173
+
174
+ * Datasets: `allstat-semantic-dev` and `allstat-semantic-test`
175
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
176
+
177
+ | Metric | allstat-semantic-dev | allstat-semantic-test |
178
+ |:--------------------|:---------------------|:----------------------|
179
+ | pearson_cosine | 0.9659 | 0.9645 |
180
+ | **spearman_cosine** | **0.8745** | **0.8646** |
181
+
182
+ <!--
183
+ ## Bias, Risks and Limitations
184
+
185
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
186
+ -->
187
+
188
+ <!--
189
+ ### Recommendations
190
+
191
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
192
+ -->
193
+
194
+ ## Training Details
195
+
196
+ ### Training Dataset
197
+
198
+ #### bps-publication-title-pairs
199
+
200
+ * Dataset: [bps-publication-title-pairs](https://huggingface.co/datasets/yahyaabd/bps-publication-title-pairs) at [4987e97](https://huggingface.co/datasets/yahyaabd/bps-publication-title-pairs/tree/4987e97a87a10fa40313e6c3efb667ed2c54775d)
201
+ * Size: 42,138 training samples
202
+ * Columns: <code>query</code>, <code>doc_title</code>, and <code>score</code>
203
+ * Approximate statistics based on the first 1000 samples:
204
+ | | query | doc_title | score |
205
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
206
+ | type | string | string | float |
207
+ | details | <ul><li>min: 5 tokens</li><li>mean: 12.33 tokens</li><li>max: 71 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 15.04 tokens</li><li>max: 77 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.53</li><li>max: 1.0</li></ul> |
208
+ * Samples:
209
+ | query | doc_title | score |
210
+ |:---------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------|:------------------|
211
+ | <code>Hasil riset mobilitas Jabodetabek tahun 2023</code> | <code>Statistik Komuter Jabodetabek Hasil Survei Komuter Jabodetabek 2023</code> | <code>0.85</code> |
212
+ | <code>Indeks harga konsumen di Indonesia tahun 2017 (82 kota)</code> | <code>Harga Konsumen Beberapa Barang dan Jasa Kelompok Sandang di 82 Kota di Indonesia 2017</code> | <code>0.15</code> |
213
+ | <code>Laporan sektor bangunan Indonesia Q4 2009</code> | <code>Indikator Konstruksi Triwulan IV Tahun 2009</code> | <code>0.91</code> |
214
+ * Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
215
+ ```json
216
+ {
217
+ "loss_fct": "torch.nn.modules.loss.MSELoss"
218
+ }
219
+ ```
220
+
221
+ ### Evaluation Dataset
222
+
223
+ #### bps-publication-title-pairs
224
+
225
+ * Dataset: [bps-publication-title-pairs](https://huggingface.co/datasets/yahyaabd/bps-publication-title-pairs) at [4987e97](https://huggingface.co/datasets/yahyaabd/bps-publication-title-pairs/tree/4987e97a87a10fa40313e6c3efb667ed2c54775d)
226
+ * Size: 2,634 evaluation samples
227
+ * Columns: <code>query</code>, <code>doc_title</code>, and <code>score</code>
228
+ * Approximate statistics based on the first 1000 samples:
229
+ | | query | doc_title | score |
230
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
231
+ | type | string | string | float |
232
+ | details | <ul><li>min: 6 tokens</li><li>mean: 12.31 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 15.19 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.55</li><li>max: 1.0</li></ul> |
233
+ * Samples:
234
+ | query | doc_title | score |
235
+ |:----------------------------------------------------|:------------------------------------------------------------------|:-----------------|
236
+ | <code>Statistik tebu Indonesia tahun 2018</code> | <code>Direktori Perusahaan Perkebunan Karet Indonesia 2018</code> | <code>0.1</code> |
237
+ | <code>Data industri makanan dan minuman 2017</code> | <code>Statistik Upah Buruh Tani di Perdesaan 2018</code> | <code>0.2</code> |
238
+ | <code>Biaya hidup di Gorontalo tahun 2018</code> | <code>Survei Biaya Hidup (SBH) 2018 Gorontalo</code> | <code>0.9</code> |
239
+ * Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
240
+ ```json
241
+ {
242
+ "loss_fct": "torch.nn.modules.loss.MSELoss"
243
+ }
244
+ ```
245
+
246
+ ### Training Hyperparameters
247
+ #### Non-Default Hyperparameters
248
+
249
+ - `eval_strategy`: steps
250
+ - `per_device_train_batch_size`: 16
251
+ - `per_device_eval_batch_size`: 16
252
+ - `num_train_epochs`: 5
253
+ - `warmup_ratio`: 0.1
254
+ - `fp16`: True
255
+
256
+ #### All Hyperparameters
257
+ <details><summary>Click to expand</summary>
258
+
259
+ - `overwrite_output_dir`: False
260
+ - `do_predict`: False
261
+ - `eval_strategy`: steps
262
+ - `prediction_loss_only`: True
263
+ - `per_device_train_batch_size`: 16
264
+ - `per_device_eval_batch_size`: 16
265
+ - `per_gpu_train_batch_size`: None
266
+ - `per_gpu_eval_batch_size`: None
267
+ - `gradient_accumulation_steps`: 1
268
+ - `eval_accumulation_steps`: None
269
+ - `torch_empty_cache_steps`: None
270
+ - `learning_rate`: 5e-05
271
+ - `weight_decay`: 0.0
272
+ - `adam_beta1`: 0.9
273
+ - `adam_beta2`: 0.999
274
+ - `adam_epsilon`: 1e-08
275
+ - `max_grad_norm`: 1.0
276
+ - `num_train_epochs`: 5
277
+ - `max_steps`: -1
278
+ - `lr_scheduler_type`: linear
279
+ - `lr_scheduler_kwargs`: {}
280
+ - `warmup_ratio`: 0.1
281
+ - `warmup_steps`: 0
282
+ - `log_level`: passive
283
+ - `log_level_replica`: warning
284
+ - `log_on_each_node`: True
285
+ - `logging_nan_inf_filter`: True
286
+ - `save_safetensors`: True
287
+ - `save_on_each_node`: False
288
+ - `save_only_model`: False
289
+ - `restore_callback_states_from_checkpoint`: False
290
+ - `no_cuda`: False
291
+ - `use_cpu`: False
292
+ - `use_mps_device`: False
293
+ - `seed`: 42
294
+ - `data_seed`: None
295
+ - `jit_mode_eval`: False
296
+ - `use_ipex`: False
297
+ - `bf16`: False
298
+ - `fp16`: True
299
+ - `fp16_opt_level`: O1
300
+ - `half_precision_backend`: auto
301
+ - `bf16_full_eval`: False
302
+ - `fp16_full_eval`: False
303
+ - `tf32`: None
304
+ - `local_rank`: 0
305
+ - `ddp_backend`: None
306
+ - `tpu_num_cores`: None
307
+ - `tpu_metrics_debug`: False
308
+ - `debug`: []
309
+ - `dataloader_drop_last`: False
310
+ - `dataloader_num_workers`: 0
311
+ - `dataloader_prefetch_factor`: None
312
+ - `past_index`: -1
313
+ - `disable_tqdm`: False
314
+ - `remove_unused_columns`: True
315
+ - `label_names`: None
316
+ - `load_best_model_at_end`: False
317
+ - `ignore_data_skip`: False
318
+ - `fsdp`: []
319
+ - `fsdp_min_num_params`: 0
320
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
321
+ - `fsdp_transformer_layer_cls_to_wrap`: None
322
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
323
+ - `deepspeed`: None
324
+ - `label_smoothing_factor`: 0.0
325
+ - `optim`: adamw_torch
326
+ - `optim_args`: None
327
+ - `adafactor`: False
328
+ - `group_by_length`: False
329
+ - `length_column_name`: length
330
+ - `ddp_find_unused_parameters`: None
331
+ - `ddp_bucket_cap_mb`: None
332
+ - `ddp_broadcast_buffers`: False
333
+ - `dataloader_pin_memory`: True
334
+ - `dataloader_persistent_workers`: False
335
+ - `skip_memory_metrics`: True
336
+ - `use_legacy_prediction_loop`: False
337
+ - `push_to_hub`: False
338
+ - `resume_from_checkpoint`: None
339
+ - `hub_model_id`: None
340
+ - `hub_strategy`: every_save
341
+ - `hub_private_repo`: None
342
+ - `hub_always_push`: False
343
+ - `gradient_checkpointing`: False
344
+ - `gradient_checkpointing_kwargs`: None
345
+ - `include_inputs_for_metrics`: False
346
+ - `include_for_metrics`: []
347
+ - `eval_do_concat_batches`: True
348
+ - `fp16_backend`: auto
349
+ - `push_to_hub_model_id`: None
350
+ - `push_to_hub_organization`: None
351
+ - `mp_parameters`:
352
+ - `auto_find_batch_size`: False
353
+ - `full_determinism`: False
354
+ - `torchdynamo`: None
355
+ - `ray_scope`: last
356
+ - `ddp_timeout`: 1800
357
+ - `torch_compile`: False
358
+ - `torch_compile_backend`: None
359
+ - `torch_compile_mode`: None
360
+ - `dispatch_batches`: None
361
+ - `split_batches`: None
362
+ - `include_tokens_per_second`: False
363
+ - `include_num_input_tokens_seen`: False
364
+ - `neftune_noise_alpha`: None
365
+ - `optim_target_modules`: None
366
+ - `batch_eval_metrics`: False
367
+ - `eval_on_start`: False
368
+ - `use_liger_kernel`: False
369
+ - `eval_use_gather_object`: False
370
+ - `average_tokens_across_devices`: False
371
+ - `prompts`: None
372
+ - `batch_sampler`: batch_sampler
373
+ - `multi_dataset_batch_sampler`: proportional
374
+
375
+ </details>
376
+
377
+ ### Training Logs
378
+ <details><summary>Click to expand</summary>
379
+
380
+ | Epoch | Step | Training Loss | Validation Loss | allstat-semantic-dev_spearman_cosine | allstat-semantic-test_spearman_cosine |
381
+ |:------:|:-----:|:-------------:|:---------------:|:------------------------------------:|:-------------------------------------:|
382
+ | 0.0380 | 100 | 0.0435 | 0.0320 | 0.7989 | - |
383
+ | 0.0759 | 200 | 0.0287 | 0.0246 | 0.8127 | - |
384
+ | 0.1139 | 300 | 0.0261 | 0.0222 | 0.8132 | - |
385
+ | 0.1519 | 400 | 0.0229 | 0.0216 | 0.8096 | - |
386
+ | 0.1898 | 500 | 0.0228 | 0.0213 | 0.8090 | - |
387
+ | 0.2278 | 600 | 0.0242 | 0.0210 | 0.8096 | - |
388
+ | 0.2658 | 700 | 0.0214 | 0.0199 | 0.8143 | - |
389
+ | 0.3037 | 800 | 0.0204 | 0.0197 | 0.8136 | - |
390
+ | 0.3417 | 900 | 0.0218 | 0.0202 | 0.8097 | - |
391
+ | 0.3797 | 1000 | 0.0228 | 0.0206 | 0.8077 | - |
392
+ | 0.4176 | 1100 | 0.0226 | 0.0192 | 0.8109 | - |
393
+ | 0.4556 | 1200 | 0.021 | 0.0202 | 0.8059 | - |
394
+ | 0.4935 | 1300 | 0.0221 | 0.0204 | 0.8053 | - |
395
+ | 0.5315 | 1400 | 0.0218 | 0.0203 | 0.8070 | - |
396
+ | 0.5695 | 1500 | 0.0229 | 0.0213 | 0.8071 | - |
397
+ | 0.6074 | 1600 | 0.0248 | 0.0202 | 0.8125 | - |
398
+ | 0.6454 | 1700 | 0.0207 | 0.0189 | 0.8116 | - |
399
+ | 0.6834 | 1800 | 0.0206 | 0.0195 | 0.8106 | - |
400
+ | 0.7213 | 1900 | 0.0202 | 0.0200 | 0.8117 | - |
401
+ | 0.7593 | 2000 | 0.0198 | 0.0193 | 0.8163 | - |
402
+ | 0.7973 | 2100 | 0.0187 | 0.0176 | 0.8204 | - |
403
+ | 0.8352 | 2200 | 0.0188 | 0.0177 | 0.8192 | - |
404
+ | 0.8732 | 2300 | 0.0192 | 0.0191 | 0.8167 | - |
405
+ | 0.9112 | 2400 | 0.0173 | 0.0176 | 0.8188 | - |
406
+ | 0.9491 | 2500 | 0.0186 | 0.0183 | 0.8212 | - |
407
+ | 0.9871 | 2600 | 0.0174 | 0.0182 | 0.8243 | - |
408
+ | 1.0251 | 2700 | 0.0148 | 0.0158 | 0.8255 | - |
409
+ | 1.0630 | 2800 | 0.0149 | 0.0162 | 0.8216 | - |
410
+ | 1.1010 | 2900 | 0.0137 | 0.0161 | 0.8273 | - |
411
+ | 1.1390 | 3000 | 0.0148 | 0.0166 | 0.8233 | - |
412
+ | 1.1769 | 3100 | 0.0138 | 0.0155 | 0.8251 | - |
413
+ | 1.2149 | 3200 | 0.0122 | 0.0154 | 0.8320 | - |
414
+ | 1.2528 | 3300 | 0.0149 | 0.0158 | 0.8293 | - |
415
+ | 1.2908 | 3400 | 0.0134 | 0.0150 | 0.8314 | - |
416
+ | 1.3288 | 3500 | 0.0141 | 0.0148 | 0.8292 | - |
417
+ | 1.3667 | 3600 | 0.0138 | 0.0140 | 0.8337 | - |
418
+ | 1.4047 | 3700 | 0.0128 | 0.0158 | 0.8256 | - |
419
+ | 1.4427 | 3800 | 0.0135 | 0.0154 | 0.8284 | - |
420
+ | 1.4806 | 3900 | 0.0142 | 0.0151 | 0.8376 | - |
421
+ | 1.5186 | 4000 | 0.0148 | 0.0145 | 0.8308 | - |
422
+ | 1.5566 | 4100 | 0.013 | 0.0146 | 0.8373 | - |
423
+ | 1.5945 | 4200 | 0.0137 | 0.0144 | 0.8296 | - |
424
+ | 1.6325 | 4300 | 0.0126 | 0.0146 | 0.8273 | - |
425
+ | 1.6705 | 4400 | 0.0138 | 0.0138 | 0.8358 | - |
426
+ | 1.7084 | 4500 | 0.0141 | 0.0144 | 0.8371 | - |
427
+ | 1.7464 | 4600 | 0.0127 | 0.0142 | 0.8339 | - |
428
+ | 1.7844 | 4700 | 0.0124 | 0.0144 | 0.8356 | - |
429
+ | 1.8223 | 4800 | 0.0126 | 0.0142 | 0.8311 | - |
430
+ | 1.8603 | 4900 | 0.0145 | 0.0137 | 0.8371 | - |
431
+ | 1.8983 | 5000 | 0.0125 | 0.0139 | 0.8336 | - |
432
+ | 1.9362 | 5100 | 0.0137 | 0.0140 | 0.8394 | - |
433
+ | 1.9742 | 5200 | 0.0127 | 0.0135 | 0.8374 | - |
434
+ | 2.0121 | 5300 | 0.0111 | 0.0135 | 0.8384 | - |
435
+ | 2.0501 | 5400 | 0.0086 | 0.0127 | 0.8404 | - |
436
+ | 2.0881 | 5500 | 0.0089 | 0.0120 | 0.8453 | - |
437
+ | 2.1260 | 5600 | 0.0091 | 0.0119 | 0.8463 | - |
438
+ | 2.1640 | 5700 | 0.0094 | 0.0125 | 0.8432 | - |
439
+ | 2.2020 | 5800 | 0.009 | 0.0126 | 0.8440 | - |
440
+ | 2.2399 | 5900 | 0.0093 | 0.0120 | 0.8469 | - |
441
+ | 2.2779 | 6000 | 0.0091 | 0.0124 | 0.8484 | - |
442
+ | 2.3159 | 6100 | 0.0101 | 0.0119 | 0.8472 | - |
443
+ | 2.3538 | 6200 | 0.0091 | 0.0125 | 0.8419 | - |
444
+ | 2.3918 | 6300 | 0.0105 | 0.0125 | 0.8409 | - |
445
+ | 2.4298 | 6400 | 0.0096 | 0.0125 | 0.8446 | - |
446
+ | 2.4677 | 6500 | 0.0099 | 0.0120 | 0.8431 | - |
447
+ | 2.5057 | 6600 | 0.0098 | 0.0124 | 0.8428 | - |
448
+ | 2.5437 | 6700 | 0.0085 | 0.0120 | 0.8444 | - |
449
+ | 2.5816 | 6800 | 0.0096 | 0.0120 | 0.8487 | - |
450
+ | 2.6196 | 6900 | 0.0094 | 0.0127 | 0.8479 | - |
451
+ | 2.6576 | 7000 | 0.0082 | 0.0116 | 0.8504 | - |
452
+ | 2.6955 | 7100 | 0.0098 | 0.0115 | 0.8509 | - |
453
+ | 2.7335 | 7200 | 0.0088 | 0.0114 | 0.8551 | - |
454
+ | 2.7715 | 7300 | 0.0081 | 0.0112 | 0.8525 | - |
455
+ | 2.8094 | 7400 | 0.0099 | 0.0114 | 0.8497 | - |
456
+ | 2.8474 | 7500 | 0.0085 | 0.0116 | 0.8527 | - |
457
+ | 2.8853 | 7600 | 0.0098 | 0.0115 | 0.8502 | - |
458
+ | 2.9233 | 7700 | 0.0093 | 0.0118 | 0.8482 | - |
459
+ | 2.9613 | 7800 | 0.0093 | 0.0117 | 0.8512 | - |
460
+ | 2.9992 | 7900 | 0.0087 | 0.0117 | 0.8517 | - |
461
+ | 3.0372 | 8000 | 0.0064 | 0.0106 | 0.8559 | - |
462
+ | 3.0752 | 8100 | 0.0059 | 0.0107 | 0.8578 | - |
463
+ | 3.1131 | 8200 | 0.0062 | 0.0106 | 0.8556 | - |
464
+ | 3.1511 | 8300 | 0.0071 | 0.0107 | 0.8526 | - |
465
+ | 3.1891 | 8400 | 0.0059 | 0.0106 | 0.8563 | - |
466
+ | 3.2270 | 8500 | 0.0065 | 0.0105 | 0.8595 | - |
467
+ | 3.2650 | 8600 | 0.0068 | 0.0105 | 0.8595 | - |
468
+ | 3.3030 | 8700 | 0.0068 | 0.0105 | 0.8588 | - |
469
+ | 3.3409 | 8800 | 0.0061 | 0.0103 | 0.8592 | - |
470
+ | 3.3789 | 8900 | 0.0067 | 0.0103 | 0.8599 | - |
471
+ | 3.4169 | 9000 | 0.0061 | 0.0102 | 0.8597 | - |
472
+ | 3.4548 | 9100 | 0.0058 | 0.0106 | 0.8604 | - |
473
+ | 3.4928 | 9200 | 0.0068 | 0.0103 | 0.8599 | - |
474
+ | 3.5308 | 9300 | 0.0058 | 0.0099 | 0.8636 | - |
475
+ | 3.5687 | 9400 | 0.0061 | 0.0100 | 0.8625 | - |
476
+ | 3.6067 | 9500 | 0.0064 | 0.0105 | 0.8590 | - |
477
+ | 3.6446 | 9600 | 0.006 | 0.0101 | 0.8590 | - |
478
+ | 3.6826 | 9700 | 0.0064 | 0.0106 | 0.8590 | - |
479
+ | 3.7206 | 9800 | 0.0059 | 0.0105 | 0.8600 | - |
480
+ | 3.7585 | 9900 | 0.0066 | 0.0102 | 0.8635 | - |
481
+ | 3.7965 | 10000 | 0.0065 | 0.0101 | 0.8617 | - |
482
+ | 3.8345 | 10100 | 0.006 | 0.0104 | 0.8628 | - |
483
+ | 3.8724 | 10200 | 0.0063 | 0.0103 | 0.8629 | - |
484
+ | 3.9104 | 10300 | 0.0064 | 0.0098 | 0.8659 | - |
485
+ | 3.9484 | 10400 | 0.0063 | 0.0098 | 0.8669 | - |
486
+ | 3.9863 | 10500 | 0.0062 | 0.0100 | 0.8647 | - |
487
+ | 4.0243 | 10600 | 0.0052 | 0.0095 | 0.8666 | - |
488
+ | 4.0623 | 10700 | 0.0045 | 0.0095 | 0.8665 | - |
489
+ | 4.1002 | 10800 | 0.004 | 0.0097 | 0.8662 | - |
490
+ | 4.1382 | 10900 | 0.0042 | 0.0095 | 0.8680 | - |
491
+ | 4.1762 | 11000 | 0.0045 | 0.0096 | 0.8676 | - |
492
+ | 4.2141 | 11100 | 0.0044 | 0.0096 | 0.8673 | - |
493
+ | 4.2521 | 11200 | 0.0043 | 0.0097 | 0.8684 | - |
494
+ | 4.2901 | 11300 | 0.0046 | 0.0094 | 0.8705 | - |
495
+ | 4.3280 | 11400 | 0.0039 | 0.0095 | 0.8699 | - |
496
+ | 4.3660 | 11500 | 0.0046 | 0.0094 | 0.8707 | - |
497
+ | 4.4039 | 11600 | 0.0041 | 0.0094 | 0.8708 | - |
498
+ | 4.4419 | 11700 | 0.0039 | 0.0093 | 0.8709 | - |
499
+ | 4.4799 | 11800 | 0.0046 | 0.0092 | 0.8720 | - |
500
+ | 4.5178 | 11900 | 0.0043 | 0.0093 | 0.8715 | - |
501
+ | 4.5558 | 12000 | 0.004 | 0.0093 | 0.8726 | - |
502
+ | 4.5938 | 12100 | 0.0043 | 0.0092 | 0.8729 | - |
503
+ | 4.6317 | 12200 | 0.0042 | 0.0092 | 0.8734 | - |
504
+ | 4.6697 | 12300 | 0.004 | 0.0091 | 0.8735 | - |
505
+ | 4.7077 | 12400 | 0.004 | 0.0092 | 0.8733 | - |
506
+ | 4.7456 | 12500 | 0.0039 | 0.0090 | 0.8743 | - |
507
+ | 4.7836 | 12600 | 0.0044 | 0.0090 | 0.8749 | - |
508
+ | 4.8216 | 12700 | 0.0041 | 0.0089 | 0.8752 | - |
509
+ | 4.8595 | 12800 | 0.004 | 0.0090 | 0.8746 | - |
510
+ | 4.8975 | 12900 | 0.004 | 0.0090 | 0.8744 | - |
511
+ | 4.9355 | 13000 | 0.0041 | 0.0090 | 0.8746 | - |
512
+ | 4.9734 | 13100 | 0.0039 | 0.0090 | 0.8745 | - |
513
+ | 5.0 | 13170 | - | - | - | 0.8646 |
514
+
515
+ </details>
516
+
517
+ ### Framework Versions
518
+ - Python: 3.10.12
519
+ - Sentence Transformers: 3.3.1
520
+ - Transformers: 4.47.1
521
+ - PyTorch: 2.5.1+cu121
522
+ - Accelerate: 1.2.1
523
+ - Datasets: 3.2.0
524
+ - Tokenizers: 0.21.0
525
+
526
+ ## Citation
527
+
528
+ ### BibTeX
529
+
530
+ #### Sentence Transformers
531
+ ```bibtex
532
+ @inproceedings{reimers-2019-sentence-bert,
533
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
534
+ author = "Reimers, Nils and Gurevych, Iryna",
535
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
536
+ month = "11",
537
+ year = "2019",
538
+ publisher = "Association for Computational Linguistics",
539
+ url = "https://arxiv.org/abs/1908.10084",
540
+ }
541
+ ```
542
+
543
+ <!--
544
+ ## Glossary
545
+
546
+ *Clearly define terms in order to be accessible across audiences.*
547
+ -->
548
+
549
+ <!--
550
+ ## Model Card Authors
551
+
552
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
553
+ -->
554
+
555
+ <!--
556
+ ## Model Card Contact
557
+
558
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
559
+ -->
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "output/training_stsbenchmark_f-2024-12-27_03-19-42/final",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertModel"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "output_hidden_states": true,
17
+ "output_past": true,
18
+ "pad_token_id": 0,
19
+ "qa_dropout": 0.1,
20
+ "seq_classif_dropout": 0.2,
21
+ "sinusoidal_pos_embds": false,
22
+ "tie_weights_": true,
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.47.1",
25
+ "vocab_size": 119547
26
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.3.1",
4
+ "transformers": "4.47.1",
5
+ "pytorch": "2.5.1+cu121"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:169bb23ce1e588f06450e3ee061c73fc0a9c0679b8c1fcb78e402db40affbff2
3
+ size 538947416
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Dense",
18
+ "type": "sentence_transformers.models.Dense"
19
+ }
20
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 128,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "full_tokenizer_file": null,
50
+ "mask_token": "[MASK]",
51
+ "max_len": 512,
52
+ "max_length": 128,
53
+ "model_max_length": 128,
54
+ "never_split": null,
55
+ "pad_to_multiple_of": null,
56
+ "pad_token": "[PAD]",
57
+ "pad_token_type_id": 0,
58
+ "padding_side": "right",
59
+ "sep_token": "[SEP]",
60
+ "stride": 0,
61
+ "strip_accents": null,
62
+ "tokenize_chinese_chars": true,
63
+ "tokenizer_class": "DistilBertTokenizer",
64
+ "truncation_side": "right",
65
+ "truncation_strategy": "longest_first",
66
+ "unk_token": "[UNK]"
67
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff